Borrowing it
Nothing to install: this file belongs to dirmacs/daedra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dirmacs/daedra/main/AGENTS.mdgit clone --depth 1 https://github.com/dirmacs/daedraWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/dirmacs/daedra/agents-md)<a href="https://agentmods.dev/instructions/dirmacs/daedra/agents-md"><img src="https://agentmods.dev/badge/instructions/dirmacs/daedra/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/dirmacs/daedra/agents-md"><img src="https://agentmods.dev/badge/instructions/dirmacs/daedra/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00848 | $0.00848 |
| Opus 5.5 | $0.00339 | $0.00339 |
| Sonnet 5.5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
daedra AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
daedra — Agent Guidelines
What this is
Daedra is a web search MCP server. It gives search and fetch tools to AI agents via MCP (Model Context Protocol). Fourteen unkeyed backends run in a fallback chain. Circuit breakers and per-backend rate limits keep search reliable from any IP.
Rules for agents
- Run
cargo testbefore you change any file. All tests must pass. - The fallback chain is the core value. Do not change the backend order in
SearchProvider::auto()without a good reason. - Each backend is independent. A new backend must not change the behavior of other backends.
- The MCP server registers tools in
src/server.rs(DaedraHandler::list_tools). The handlers arehandle_web_search,handle_visit_page, andhandle_crawl_site. - Tool names:
web_search(primary),search_duckduckgo(backward-compatibility alias),visit_page,crawl_site. - The cache layer is transparent. Backends do not know that the cache exists.
- Do not hardcode paths or API keys in source code. All configuration comes from environment variables or CLI arguments.
Module map
| Path | Role |
|---|---|
src/main.rs |
CLI entry — Commands::run, CheckReporter for daedra check |
src/server.rs |
MCP server, transports, DaedraHandler tool dispatch |
src/lib.rs |
Crate root, re-exports |
src/url_classification.rs |
Data-driven URL → ContentType rules for search results |
src/tools/backend.rs |
SearchProvider, BackendHealth circuit breakers, governor keyed limiters, classified retry, aggregate failure messages |
src/tools/rss.rs |
Machine-format backends: Bing RSS, Google News RSS, HN Algolia |
src/tools/soft_block.rs |
Zero-result page classifier: genuine no-results or soft block |
src/tools/fetch.rs |
FetchClient, FetchedContent (Html/Pdf/Document/Text/Binary), dom_smoothie, infer, pdf-inspector, anydoc |
src/tools/crawl.rs |
Site crawl (sitemap + link following) |
src/tools/bing.rs, src/tools/google.rs |
HTML scraper backends |
src/tools/*.rs |
Other individual search backends |
src/cache.rs |
moka async cache layer |
src/types.rs |
Shared types; detect_language / detect_topics use data-driven tables |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 49 lines · 848 tokens per session scan A afe60583a9c0
daedra AGENTS.md is an instructions file published in the GitHub repository dirmacs/daedra (17 stars, last pushed today), licensed MIT. It adds 848 tokens to every session, about $0.0034 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.